Bewitch
Romantic AI companion for immersive roleplay conversations.
What it does
Most AI companion apps either feel robotic or jump straight into explicit content. Bewitch focuses on romantic tension, immersive roleplay, and conversations that evolve naturally over time, the space in between. Available in 5 languages, with both curated characters and fully customizable AI personas. Built for people looking for emotional immersion, not just another chatbot.
Does the same job
all alternatives →- WLWhisperFusion – Low-latency conversations with an AI chatbot2024 · github.com · ▲272
WhisperFusion builds upon the capabilities of open source tools WhisperLive and WhisperSpeech to provide a seamless conversations with an AI chatbot.
- BTBe the ChatBOTJul 2026 · bethechatbot.com · ▲55
I made this experimental art project/game that's an LLM chat assistant, but where you're the AI. I wanted people to get a visceral sense of what it's like to answer the kinds of things that people prompt their chatbots day in and day out. If you're interested, I wrote up some more info on how I made it, including how the "user" prompts are generated with an eye for realism: https://bethechatbot.com/about Hope you enjoy it! I'd love to hear people's takeaways.
- RFRoleplay-first chat UI for an OpenAI-compatible chat completions APIJan 2026 · abliteration.ai · ▲10
I built a dedicated roleplay chat UI for abliteration.ai: https://abliteration.ai/roleplay The backend is OpenAI-compatible (/v1/chat/completions), with usage-based pricing and no prompt/output retention by default (details on the site). The UI is meant for long-form character chats and interactive fiction, without needing a local frontend. Docs (including a roleplay backend guide and a SillyTavern integration guide): https://abliteration.ai/docs Would love feedback on missing RP features, UX rough edges, and what you would expect from a…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com